Agent Framework Azure Ai Py
v0.1.0Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.
⭐ 1· 2k·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md content clearly implements an Azure Agent Framework helper (creating agents, tools, threads, streaming). That purpose is coherent. However, the skill metadata declares no required environment variables or primary credential, while the runtime instructions repeatedly reference AZURE_AI_PROJECT_ENDPOINT, AZURE_AI_MODEL_DEPLOYMENT_NAME, BING_CONNECTION_ID, and use Azure credentials (AzureCliCredential / DefaultAzureCredential). The metadata omission is an inconsistency that could hide required privileged access.
Instruction Scope
Instructions are detailed and mostly within scope (agent creation, tools, streaming, threads). They include sample code that: (1) creates HTTP clients with Authorization headers (bearer tokens), (2) references uploading files and downloading file IDs, (3) saves conversation/thread IDs to disk (conversation.json), and (4) uses environment variables like BING_CONNECTION_ID and github_pat in examples. The instructions therefore expect access to credentials and potentially internal MCP endpoints; those accesses are not reflected in the declared requirements and expand the runtime data surface.
Install Mechanism
This is an instruction-only skill (no install spec, no code files). That minimizes disk-write/install risk; there is no remote download step to analyze.
Credentials
Although the registry metadata lists no required env vars or primary credential, the SKILL.md repeatedly expects Azure credentials and several environment values (AZURE_AI_PROJECT_ENDPOINT, AZURE_AI_MODEL_DEPLOYMENT_NAME, BING_CONNECTION_ID, BING_CUSTOM_CONNECTION_ID, github_pat in an example, and bearer tokens for MCP headers). Asking for Azure credentials and token-bearing headers is reasonable for this functionality, but the metadata should declare them — the omission is disproportionate and reduces transparency about what secrets you must provide.
Persistence & Privilege
always:false and default autonomous invocation are normal. The skill's examples persist conversation/thread IDs to a file and show usage of server-managed persistent agents and MCP integrations. Writing conversation metadata to disk and connecting to external MCP endpoints are expected for persistent agent scenarios, but you should be aware persistent agents and MCP tools can access and store conversation context and may call external services.
What to consider before installing
This skill appears to be a legitimate set of usage examples for the Microsoft Agent Framework on Azure, but the SKILL.md requires credentials and environment variables that the skill metadata does not declare. Before installing or using it:
- Treat it as code examples, not a packaged binary; nothing is installed, but the runtime will require Azure credentials (use AzureCliCredential or DefaultAzureCredential) and may need BING_CONNECTION_ID or other tokens for hosted web search or MCP access.
- Do not reuse high-privilege secrets: test with a least-privilege Azure identity or a separate test subscription.
- Verify any MCP endpoint you configure (the examples allow setting custom URLs and Authorization headers) — only connect to MCP servers you control or fully trust.
- Be cautious about providing GitHub PATs, bearer tokens, or other API keys referenced in examples; only supply them when you understand exactly which tool or endpoint needs them.
- If you plan to persist conversation IDs or save threads to disk, ensure that files (eg. conversation.json) are stored in a safe location and do not contain secrets.
- Prefer to obtain the skill from a verifiable source (repository/homepage) — the registry metadata lists no homepage; ask the publisher for provenance.
If you want to proceed, request updated metadata that declares the exact environment variables and credential types required, or run the examples in an isolated environment with limited privileges first.Like a lobster shell, security has layers — review code before you run it.
latestvk97aqq6fthax82wggnrt1a749n8096d4
License
MIT-0
Free to use, modify, and redistribute. No attribution required.